> ## Documentation Index
> Fetch the complete documentation index at: https://openrouter.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# CreatePrivateEndpointRequest

## Fields

| Field | Type | Required | Description | Example |
| - | - | - | - | - |
| `activate` | [Optional\[components.PrivateEndpointActivation\]](../components/privateendpointactivation.mdx) | :heavy\_minus\_sign: | Validate and activate in the same call. On a failed validation the draft is kept and returned with a 422, so fix it and call `/validate` and `/activate` instead of creating it again. | \{<br />"workspace\_id": "550e8400-e29b-41d4-a716-446655440000"<br />} |
| `base_url` | *Optional\[str]* | :heavy\_minus\_sign: | HTTPS base URL of your deployment. Required unless the provider derives its URL from the BYOK credential (Azure, Amazon Bedrock, Google Vertex). | [https://contoso.openai.azure.com](https://contoso.openai.azure.com) |
| `declared_region` | [OptionalNullable\[components.CreatePrivateEndpointRequestDeclaredRegion\]](../components/createprivateendpointrequestdeclaredregion.mdx) | :heavy\_minus\_sign: | Attest where this deployment processes data. | us |
| `declared_zdr` | *OptionalNullable\[bool]* | :heavy\_minus\_sign: | Attest that this deployment retains no prompt or completion data. | |
| `model_permaslug` | *str* | :heavy\_check\_mark: | Permanent slug of the model this endpoint serves. | openai/gpt-4o-2024-08-06 |
| `pricing` | [Optional\[components.PrivateEndpointPricing\]](../components/privateendpointpricing.mdx) | :heavy\_minus\_sign: | Negotiated per-token rates reported for requests routed to this endpoint. | \{<br />"completion": "0.00001",<br />"prompt": "0.0000025"<br />} |
| `provider_slug` | *str* | :heavy\_check\_mark: | Slug of the upstream provider. | azure |
| `upstream_model_id` | *str* | :heavy\_check\_mark: | Model or deployment identifier sent to the upstream provider. | gpt-4o-prod |
